{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:21:01Z","timestamp":1773001261777,"version":"3.50.1"},"reference-count":41,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T00:00:00Z","timestamp":1745366400000},"content-version":"vor","delay-in-days":112,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62463002"],"award-info":[{"award-number":["62463002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473033"],"award-info":[{"award-number":["62473033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["L231012"],"award-info":[{"award-number":["L231012"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>The goal of the feature reconstruction network based on an autoencoder in the training phase is to force the network to reconstruct the input features well. The network tends to learn shortcuts of \u201cidentity mapping,\u201d which leads to the network outputting abnormal features as they are in the inference phase. As such, the abnormal features based on reconstruction error cannot be distinguished from normal features, significantly limiting the detection performance of such methods. To address this issue, we propose a feature transformation reconstruction (FTR) network, which can avoid the identity mapping problem. Specifically, we use a normalizing flow model as a feature transformation (FT) network to transform input features into other forms. The training goal of the feature reconstruction (FR) network is no longer to reconstruct the input features but to reconstruct the transformed features, effectively avoiding the shortcut of learning the \u201cidentity map.\u201d Furthermore, this paper proposes a masked convolutional attention (MCA) module, which randomly masks the input features in the training phase and reconstructs the input features in a self\u2010supervised manner. In the testing phase, the MCA can effectively suppress the excessive reconstruction of abnormal features and further improve anomaly detection performance. FTR achieves the scores of the area under the receiver operating characteristic curve (AUROC) at 99.5% and 97.8% on the MVTec AD and BTAD datasets, respectively, outperforming other state\u2010of\u2010the\u2010art methods. Moreover, FTR is faster than the existing methods, with a high speed of 137 frames per second (FPS) on a 3080ti GPU.<\/jats:p>","DOI":"10.1155\/int\/1780499","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T04:34:58Z","timestamp":1745382898000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Feature Transformation Reconstruction (FTR) Network for Unsupervised Anomaly Detection"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1261-0442","authenticated-orcid":false,"given":"Linna","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8631-1749","authenticated-orcid":false,"given":"Lanyao","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3243-5693","authenticated-orcid":false,"given":"Qi","family":"Cao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-6196","authenticated-orcid":false,"given":"Shichao","family":"Kan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-9422","authenticated-orcid":false,"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6121-9472","authenticated-orcid":false,"given":"Fugui","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6614-2608","authenticated-orcid":false,"given":"Yansen","family":"Huang","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,4,23]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.09.037"},{"key":"e_1_2_10_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2014.2311995"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2017.2664658"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2015.2488285"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.10.006"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16040717"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108213"},{"key":"e_1_2_10_8_2","doi-asserted-by":"crossref","unstructured":"ChangY. TuZ. XieW. andYuanJ. Clustering Driven Deep Autoencoder for Video Anomaly Detection Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference Proceedings Part XV 16 August 23\u201328 2020 Glasgow UK Springer 329\u2013345.","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"ChongY. S.andTayY. H. Abnormal Event Detection in Videos Using Spatiotemporal Autoencoder Proceedings of the Advances in Neural Networks-ISNN 2017: 14th International Symposium ISNN 2017 Proceedings Part II 14 June 21\u201326 2017 Hokkaido Japan Springer 189\u2013196.","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"HasanM. ChoiJ. NeumannJ. Roy-ChowdhuryA. K. andDavisL. S. Learning Temporal Regularity in Video Sequences Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016 Las Vegas 733\u2013742 https:\/\/doi.org\/10.1109\/cvpr.2016.86 2-s2.0-84986265779.","DOI":"10.1109\/CVPR.2016.86"},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"RavanbakhshM. NabiM. SanginetoE. MarcenaroL. RegazzoniC. andSebeN. Abnormal Event Detection in Videos Using Generative Adversarial Nets Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP) September 17\u201320 2017 Beijing China IEEE 1577\u20131581.","DOI":"10.1109\/ICIP.2017.8296547"},{"key":"e_1_2_10_12_2","unstructured":"BochkovskiyA. WangC.-Y. andLiaoH.-Y. M. Yolov4: Optimal Speed and Accuracy of Object Detection 2020 https:\/\/arxiv.org\/abs\/2004.10934."},{"key":"e_1_2_10_13_2","first-page":"691","article-title":"You Only Learn One Representation: Unified Network for Multiple Tasks","volume":"39","author":"Wang C.","year":"2023","journal-title":"Journal of Information Science and Engineering"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"ZhuX. LyuS. WangX. andZhaoQ. Tph-yolov5: Improved Yolov5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios Proceedings of the IEEE\/CVF International Conference on Computer Vision October 11\u201317 2021 Montreal Canada 2778\u20132788 https:\/\/doi.org\/10.1109\/iccvw54120.2021.00312.","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.61603\/ceas.v2i1.33"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22582"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"DengJ. DongW. SocherR. LiL.-J. LiK. andFei-FeiL. Imagenet: A Large-Scale Hierarchical Image Database Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition June 20\u201325 2009 Miami IEEE 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3193699"},{"key":"e_1_2_10_21_2","unstructured":"RothK. PemulaL. ZepedaJ. Sch\u00f6lkopfB. BroxT. andGehlerP. Towards Total Recall in Industrial Anomaly Detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 18\u201324 2022 New Orleans 14318\u201314328."},{"key":"e_1_2_10_22_2","unstructured":"RudolphM. WehrbeinT. RosenhahnB. andWandtB. Fully Convolutional Cross-Scale-Flows for Image-Based Defect Detection Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision January 3\u20138 2022 Waikoloa 1088\u20131097."},{"key":"e_1_2_10_23_2","unstructured":"YuJ. ZhengY. WangX.et al. Fastflow: Unsupervised Anomaly Detection and Localization via 2d Normalizing Flows 2021 https:\/\/arxiv.org\/abs\/2111.07677."},{"key":"e_1_2_10_24_2","unstructured":"DengH.andLiX. Anomaly Detection Via Reverse Distillation From One-Class Embedding Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 18\u201324 2022 New Orleans 9737\u20139746."},{"key":"e_1_2_10_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.11.018"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22974"},{"key":"e_1_2_10_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.12.008"},{"key":"e_1_2_10_28_2","first-page":"298","article-title":"Adtr: Anomaly Detection Transformer With Feature Reconstruction","author":"You Z.","year":"2022","journal-title":"Lecture Notes in Computer Science"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/7773481"},{"key":"e_1_2_10_30_2","doi-asserted-by":"crossref","unstructured":"BergmannP. FauserM. SattleggerD. andStegerC. Mvtec Ad\u2013A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 15\u201320 2019 Long Beach 9592\u20139600.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"e_1_2_10_31_2","doi-asserted-by":"crossref","unstructured":"MishraP. VerkR. FornasierD. PiciarelliC. andForestiG. L. Vt-adl: A Vision Transformer Network for Image Anomaly Detection and Localization 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE) June 20\u201323 2021 Kyoto Japan IEEE 1\u20136.","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"e_1_2_10_32_2","unstructured":"CohenN.andHoshenY. Sub-Image Anomaly Detection With Deep Pyramid Correspondences 2020 https:\/\/arxiv.org\/abs\/2005.02357."},{"key":"e_1_2_10_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"e_1_2_10_34_2","unstructured":"DinhL. Sohl-DicksteinJ. andBengioS. Density Estimation Using Real Nvp 2022 https:\/\/arxiv.org\/abs\/1605.08803."},{"key":"e_1_2_10_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107706"},{"key":"e_1_2_10_36_2","unstructured":"TanM.andLeQ. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks Proceedings of the International Conference on Machine Learning June 9\u201315 2019 Long Beach PMLR 6105\u20136114."},{"key":"e_1_2_10_37_2","unstructured":"KingmaD.andBaJ. Adam: A Method for Stochastic Optimization 2014 https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"e_1_2_10_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3182385"},{"key":"e_1_2_10_39_2","doi-asserted-by":"crossref","unstructured":"TienT. D. NguyenA. T. TranN. H.et al. Revisiting Reverse Distillation for Anomaly Detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 17\u201324 2023 Vancouver Canada 24511\u201324520 https:\/\/doi.org\/10.1109\/cvpr52729.2023.02348.","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"LiuZ. ZhouY. XuY. andWangZ. Simplenet: A Simple Network for Image Anomaly Detection and Localization Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 17\u201324 2023 Vancouver Canada 20402\u201320411 https:\/\/doi.org\/10.1109\/cvpr52729.2023.01954.","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"e_1_2_10_41_2","unstructured":"BaeJ. LeeJ.-H. andKimS. Pni: Industrial Anomaly Detection Using Position and Neighborhood Information Proceedings of the IEEE\/CVF International Conference on Computer Vision October 1\u20136 2023 Paris France 6373\u20136383."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1780499","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/1780499","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/1780499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:56:44Z","timestamp":1772992604000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/1780499"}},"subtitle":[],"editor":[{"given":"Zhiyuan","family":"Qi","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/1780499"],"URL":"https:\/\/doi.org\/10.1155\/int\/1780499","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"1780499"}}